Search system using user behavior data

• US 20050125382A1
• Filed: 12/03/2003
• Published: 06/09/2005
• Est. Priority Date: 12/03/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Dumais, Susan T., Shimizu, Takeshi, Wang, Lu, Zhang, Ying, Karnawat, Kuldeep, Taylor, Thomas A., White, Thomas D., Mydland, Mark B., Fox, Steven C.
• Granted Patent: US 7,363,282 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

Context-based user feedback is gathered regarding searches performed on a search mechanism. The search mechanism is monitored for user behavior data regarding an interaction of a user with the search mechanism. The response data provided by the search mechanism is also monitored. Context data (describing the search) and user feedback data (the user'"'"'s feedback on the search—either explicit or implicit) are determined. This can be used, for example, to evaluate a search mechanism or to check a relevance model.

Claims

1. A method for gathering context-based user feedback for a search mechanism, where said search mechanism is adapted to perform a search in response to user inputs and where at least one user has access to said search mechanism, said method comprising:

monitoring of said search mechanism for user behavior data regarding an interaction of one of said at least one users with said search mechanism to perform a search;

monitoring said search mechanism for search mechanism response data regarding said search;

determining context data describing said search; and

determining user feedback data describing said search.

2. The method of claim 1, where said search mechanism is a web browser and where said user behavior data comprises data concerning the firing of one or more events, where each of said events is fired when a corresponding user behavior occurs.

3. The method of claim 2, where said corresponding user behavior is selected from the group comprising:

entering a search query;

said user navigation to a new page using a hyperlink;

said user navigation to a new page using a history list;

said user navigation to a new page using an address bar;

said user navigation to a new page using a favorites list;

user scrolling behavior;

user document printing behavior;

said user adding a document to said favorites list;

said user switching focus to a different application;

said user switching focus back from a different application; and

said user closing a window.

4. The method of claim 1, where said search mechanism is a web browser and where said search mechanism response data regarding said search comprises a results list.

5. The method of claim 1 where said method further comprises:

tracking, using a state machine comprising at least two states describing progress through said search, which of said states said search is in.

6. The method of claim 5, where said context data describing said search comprises state data regarding which of said states were tracked during said search.

7. The method of claim 5 where at least one transition between said states in said state machines is at least partially dependent on explicit user feedback.

8. The method of claim 7 where said context data describing said search comprises said explicit user feedback.

9. The method of claim 1 where said context data describing said search comprises user behavior data.

10. The method of claim 1 where said user feedback data comprises explicit user feedback.

11. The method of claim 1 where said user feedback data comprises implicit user feedback based on said user behavior data.

12. A computer-readable medium having computer-executable instructions to perform the method of claim 1.

13. A system for gathering context-based user feedback for a search mechanism, where said search mechanism is adapted to perform a search in response to user inputs and where at least one user has access to said search mechanism, said method comprising:

a monitoring helper for monitoring of said search mechanism for user behavior data regarding an interaction of one of said at least one users with said search mechanism to perform a search and for monitoring said search mechanism for search mechanism response data regarding said search;

a user behavior tracer for determining context data describing said search and for determining user feedback data describing said search.

14. The system of claim 13, where said search mechanism is a web browser and where said user behavior data comprises data concerning the firing of one or more events, where each of said events is fired when a corresponding user behavior occurs.

15. The system of claim 14, where said corresponding user behavior is selected from the group comprising:

entering a search query;

said user navigation to a new page using a hyperlink;

said user navigation to a new page using a history list;

said user navigation to a new page using an address bar;

said user navigation to a new page using a favorites list;

user scrolling behavior;

user document printing behavior;

said user adding a document to said favorites list;

said user switching focus to a different application;

said user switching focus back from a different application; and

said user closing a window.

16. The system of claim 13, where said search mechanism is a web browser and where said search mechanism response data regarding said search comprises a results list.

17. The system of claim 13, where said user behavior tracer further comprises:

a state machine comprising at least two states describing progress through said search and tracking which of said states said search is in.

18. The system of claim 17, where said context data describing said search comprises state data regarding which of said states were tracked during said search.

19. The system of claim 17 where at least one transition between said states in said state machines is at least partially dependent on explicit user feedback.

20. The system of claim 19 where said context data describing said search comprises said explicit user feedback.

21. The system of claim 13 where said context data describing said search comprises user behavior data.

22. The system of claim 13 where said user feedback data comprises explicit user feedback.

23. The system of claim 13 where said user feedback data comprises implicit user feedback based on said user behavior data.

24. A method for testing a relevance model, where said relevance model provides a prediction for user satisfaction with a search performed on a search mechanism, and where said search mechanism is adapted to perform a search in response to user inputs and where at least one user has access to said search mechanism, said method comprising:

monitoring of said search mechanism for user behavior data regarding an interaction of one of said at least one users with said search mechanism to perform a search;

monitoring said search mechanism for search mechanism response data regarding said search;

determining context data describing said search;

determining user feedback data describing said search; and

comparing said user feedback data with said prediction from said relevance model.

25. A method for evaluating the performance of a search mechanism, where said search mechanism is adapted to perform a search in response to user inputs and where at least one user has access to said search mechanism, said method comprising:

monitoring of said search mechanism for user behavior data regarding an interaction of one of said at least one users with said search mechanism to perform a search;

monitoring said search mechanism for search mechanism response data regarding said search;

determining context data describing said search;

determining user feedback data describing user satisfaction with said search; and

evaluating said user feedback data..